© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50738
    Prev
    Next
    INDEX
    Explanations

    abelian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    翼翼
    -0.10
    FUL
    -0.09
    ä¸į误
    -0.08
    éĩįéĩįçļĦ
    -0.08
    trup
    -0.08
    leos
    -0.08
    fulness
    -0.08
    SSION
    -0.08
    erval
    -0.08
    .definition
    -0.08
    POSITIVE LOGITS
    ized
    0.08
    ness
    0.07
    ity
    0.07
    ridged
    0.07
    /non
    0.07
    ieved
    0.07
    m
    0.06
    èī¯å¿ĥ
    0.06
    åĴĮéĿŀ
    0.06
    ization
    0.06
    Activations Density 0.002%

    No Known Activations